# Active Learning for Sound Event Detection

arXiv: https://arxiv.org/abs/2002.05033 · HTML: https://mlsanity.com/paper/2002.05033/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2020.

## Built on by (most cited first, 14 of 14)

- [Correlation Clustering with Active Learning of Pairwise Similarities](https://mlsanity.com/paper/2302.10295/) (2023)
- [A Unified Active Learning Framework for Annotating Graph Data with Application to Software Source Code Performance Prediction](https://mlsanity.com/paper/2304.13032/) (2023)
- [Deep Active Audio Feature Learning in Resource-Constrained Environments](https://mlsanity.com/paper/2308.13201/) (2023)
- [Latent Neural Stochastic Differential Equations for Change Point Detection](https://mlsanity.com/paper/2208.10317/) (2022)
- [Enhancing RAG with Active Learning on Conversation Records: Reject Incapables and Answer Capables](https://mlsanity.com/paper/2502.09073/) (2025)
- [Aggregation Strategies for Efficient Annotation of Bioacoustic Sound Events Using Active Learning](https://mlsanity.com/paper/2503.02422/) (2025)
- [Hybrid Disagreement-Diversity Active Learning for Bioacoustic Sound Event Detection](https://mlsanity.com/paper/2505.20956/) (2025)
- [Perception and Semantic Aware Regularization for Sequential Confidence Calibration](https://mlsanity.com/paper/2305.19498/) (2023)
- [Information-Theoretic Active Correlation Clustering](https://mlsanity.com/paper/2402.03587/) (2024)
- [Evaluating Interactive 2D Visualization as a Sample Selection Strategy for Biomedical Time-Series Data Annotation](https://mlsanity.com/paper/2603.26592/) (2026)
- [Improving the quality control of seismic data through active learning](https://mlsanity.com/paper/2201.06616/) (2022)
- [A Data-Centric Framework for Machine Listening Projects: Addressing Large-Scale Data Acquisition and Labeling through Active Learning](https://mlsanity.com/paper/2405.18153/) (2024)
- [Greedy Volume Maximization of Gradient Embeddings for Long-Tailed Frame-Level Bioacoustic Active Learning](https://mlsanity.com/paper/2607.13555/) (2026)
- [Cover First, Disagree Softly: Rethinking Mismatch-First Active Learning for Frame-Level Audio Classification](https://mlsanity.com/paper/2607.13571/) (2026)

## Abstract (arXiv)

This paper proposes an active learning system for sound event detection (SED). It aims at maximizing the accuracy of a learned SED model with limited annotation effort. The proposed system analyzes an initially unlabeled audio dataset, from which it selects sound segments for manual annotation. The candidate segments are generated based on a proposed change point detection approach, and the selection is based on the principle of mismatch-first farthest-traversal. During the training of SED models, recordings are used as training inputs, preserving the long-term context for annotated segments. The proposed system clearly outperforms reference methods in the two datasets used for evaluation (TUT Rare Sound 2017 and TAU Spatial Sound 2019). Training with recordings as context outperforms training with only annotated segments. Mismatch-first farthest-traversal outperforms reference sample selection methods based on random sampling and uncertainty sampling. Remarkably, the required annotation effort can be greatly reduced on the dataset where target sound events are rare: by annotating only 2% of the training data, the achieved SED performance is similar to annotating all the training data.